search

YiLunLee / missing_aware_prompts

Multimodal Prompting with Missing Modalities for Visual Recognition, CVPR'23
https://yilunlee.github.io/missing_aware_prompts/
175 stars 12 forks source link

Implementation Details #26

Open HYC01 opened 3 months ago

HYC01 commented 3 months ago

python run.py with data_root=./datasets/mmimdb
num_gpus=1
num_nodes=1
per_gpu_batchsize=4
task_finetune_mmimdb
load_path=./pretrained_weights/vilt_200k_mlm_itm.ckpt
exp_name=./output/mmimdb

Thanks for your impressive work, Following the above training setting, I got the results "40.23" on mmimdb dataset. So l will appreciate if you can provide more details about training settings. Thanks for your time!